Related papers: Measuring Intersectional Biases in Historical Docu…

Optical Character Recognition (OCR) is a critical but error-prone stage in digital humanities text pipelines. While OCR correction improves usability for downstream NLP tasks, common workflows often overwrite intermediate decisions,…

Effects of Optical Character Recognition (OCR) quality on historical information retrieval have so far been studied in data-oriented scenarios regarding the effectiveness of retrieval results. Such studies have either focused on the effects…

Despite well-documented consequences of the U.S. government's 1930s housing policies on racial wealth disparities, scholars have struggled to quantify its precise financial effects due to the inaccessibility of historical property appraisal…

The manifestation and effect of bias in news reporting have been central topics in the social sciences for decades, and have received increasing attention in the NLP community recently. While NLP can help to scale up analyses or contribute…

Natural Language Processing (NLP) models have been found discriminative against groups of different social identities such as gender and race. With the negative consequences of these undesired biases, researchers have responded with…

Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such methods are too…

Language can be used as a means of reproducing and enforcing harmful stereotypes and biases and has been analysed as such in numerous research. In this paper, we present a survey of 304 papers on gender bias in natural language processing.…

In this paper, we investigate the usage of fine-grained font recognition on OCR for books printed from the 15th to the 18th century. We used a newly created dataset for OCR of early printed books for which fonts are labeled with bounding…

This work describes a large-scale analysis of sentiment associations in popular word embedding models along the lines of gender and ethnicity but also along the less frequently studied dimensions of socioeconomic status, age, sexual…

Debiasing word embeddings has been largely limited to individual and independent social categories. However, real-world corpora typically present multiple social categories that possibly correlate or intersect with each other. For instance,…

Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings…

Word embeddings learnt from massive text collections have demonstrated significant levels of discriminative biases such as gender, racial or ethnic biases, which in turn bias the down-stream NLP applications that use those word embeddings.…

The use of abusive language online has become an increasingly pervasive problem that damages both individuals and society, with effects ranging from psychological harm right through to escalation to real-life violence and even death.…

As natural language processing systems become more widespread, it is necessary to address fairness issues in their implementation and deployment to ensure that their negative impacts on society are understood and minimized. However, there…

Researchers have devised numerous ways to quantify social biases vested in pretrained language models. As some language models are capable of generating coherent completions given a set of textual prompts, several prompting datasets have…

This paper presents our methodology and findings from three tasks across Optical Character Recognition (OCR) and Document Layout Analysis using advanced deep learning techniques. First, for the historical Hebrew fragments of the Dead Sea…

Bias-measuring datasets play a critical role in detecting biased behavior of language models and in evaluating progress of bias mitigation methods. In this work, we focus on evaluating gender bias through coreference resolution, where…

This paper presents a computational method of analysis that draws from machine learning, library science, and literary studies to map the visual layouts of multi-ethnic newspapers from the late 19th and early 20th century United States.…

Language models are trained on large-scale corpora that embed implicit biases documented in psychology. Valence associations (pleasantness/unpleasantness) of social groups determine the biased attitudes towards groups and concepts in social…

Intersectionality is a framework that analyzes how interlocking systems of power and oppression affect individuals along overlapping dimensions including race, gender, sexual orientation, class, and disability. Intersectionality theory…